The search for prevalent combinations of chemicals in women of childbearing age-presentation

This presentation will examine an approach for analyzing NHANES data using frequent itemset mining (FIM), a technique traditionally used for market basket analysis. We analyzed data from the 2009-2010 cycle of the continuous National Health and Nutrition Examination Survey (NHANES) to identify combinations of chemicals that frequently co-occur in people. We identified 90 chemical combinations consisting of relatively few chemicals that occur in at least 30% of the U.S. population. We also applied the method to a curated NHANES data set including only women of childbearing age. These subjects were weighted based on demographically-based birth rates in order to predict potentially prevalent combination exposures for in utero human fetuses. This work demonstrated how FIM can be used in conjunction with biomonitoring data to narrow a large number of possible chemical combinations down to a smaller set of prevalent chemical combinations.

Impact/Purpose

These slides will be presented at a plenary lecture at the North Carolina Society of Toxicology (NC SOT) Annual meeting on October 7, 2019. The title for this talk is “The Search for Prevalent Combinations of Chemicals in Women of Childbearing Age,” but most of the slides focus on the underlying method, which is called frequent itemset mining (FIM).

Citation

Kapraun, D. The search for prevalent combinations of chemicals in women of childbearing age-presentation. North Carolina Society of Toxicology Annual Meeting, Durham, NC, October 07, 2019.